Graph Adversarial Immunization for Certifiable Robustness
share
Despite achieving great success, graph neural networks (GNNs) are vulnerable to adversarial attacks. Existing defenses focus on developing adversarial training or robust GNNs. However, little research attention is paid to the potential and practice of immunization on graphs. In this paper, we propose and formulate graph adversarial immunization, i.e., vaccinating part of graph structure to improve certifiable robustness of graph against any admissible adversarial attack. We first propose edge-level immunization to vaccinate node pairs. Despite the primary success, such edge-level immunization cannot defend against emerging node injection attacks, since it only immunizes existing node pairs. To this end, we further propose node-level immunization. To circumvent computationally expensive combinatorial optimization when solving adversarial immunization, we design AdvImmune-Edge and AdvImmune-Node algorithms to effectively obtain the immune node pairs or nodes. Experiments demonstrate the superiority of AdvImmune methods. In particular, AdvImmune-Node remarkably improves the ratio of robust nodes by 79 only 5 performance against various attacks, outperforming state-of-the-art defenses. To the best of our knowledge, this is the first attempt to improve certifiable robustness from graph data perspective without losing performance on clean graphs, providing new insights into graph adversarial learning.
READ FULL TEXT